English
Related papers

Related papers: FlattenGPT: Depth Compression for Transformer with…

200 papers

The resource requirements of neural networks can be significantly reduced through pruning - the removal of seemingly less important parameters. However, for LLMs, full retraining to recover pruning-induced performance degradation is often…

Machine Learning · Computer Science 2026-02-03 Max Zimmer , Christophe Roux , Moritz Wagner , Deborah Hendrych , Sebastian Pokutta

Deep Learning models have become the dominant approach in several areas due to their high performance. Unfortunately, the size and hence computational requirements of operating such models can be considerably high. Therefore, this…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Abdullah Salama , Oleksiy Ostapenko , Tassilo Klein , Moin Nabi

This paper presents a novel differentiable method for unstructured weight pruning of deep neural networks. Our learned-threshold pruning (LTP) method learns per-layer thresholds via gradient descent, unlike conventional methods where they…

Machine Learning · Computer Science 2021-03-22 Kambiz Azarian , Yash Bhalgat , Jinwon Lee , Tijmen Blankevoort

Model pruning aims to reduce the deep neural network (DNN) model size or computational overhead. Traditional model pruning methods such as l-1 pruning that evaluates the channel significance for DNN pay too much attention to the local…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Xinyu Liu , Baopu Li , Zhen Chen , Yixuan Yuan

Convolutional Neural Networks (CNN) are becoming a common presence in many applications and services, due to their superior recognition accuracy. They are increasingly being used on mobile devices, many times just by porting large models…

Machine Learning · Computer Science 2020-02-21 Valentin Radu , Kuba Kaszyk , Yuan Wen , Jack Turner , Jose Cano , Elliot J. Crowley , Bjorn Franke , Amos Storkey , Michael O'Boyle

Transformer architecture has gained popularity due to its ability to scale with large dataset. Consequently, there is a need to reduce the model size and latency, especially for on-device deployment. We focus on vision transformer proposed…

Computer Vision and Pattern Recognition · Computer Science 2022-03-28 Ankur Kumar

Pruning is an effective way to reduce the huge inference cost of Transformer models. However, prior work on pruning Transformers requires retraining the models. This can add high training cost and high complexity to model deployment, making…

Computation and Language · Computer Science 2022-10-18 Woosuk Kwon , Sehoon Kim , Michael W. Mahoney , Joseph Hassoun , Kurt Keutzer , Amir Gholami

In recent years, deep neural networks have achieved great success in the field of computer vision. However, it is still a big challenge to deploy these deep models on resource-constrained embedded devices such as mobile robots, smart phones…

Computer Vision and Pattern Recognition · Computer Science 2018-05-30 Yiming Hu , Siyang Sun , Jianquan Li , Xingang Wang , Qingyi Gu

Network compression has been widely studied since it is able to reduce the memory and computation cost during inference. However, previous methods seldom deal with complicated structures like residual connections, group/depth-wise…

Computer Vision and Pattern Recognition · Computer Science 2021-08-03 Liyang Liu , Shilong Zhang , Zhanghui Kuang , Aojun Zhou , Jing-Hao Xue , Xinjiang Wang , Yimin Chen , Wenming Yang , Qingmin Liao , Wayne Zhang

Large Language Models (LLMs) have reshaped the landscape of artificial intelligence by demonstrating exceptional performance across various tasks. However, substantial computational requirements make their deployment challenging on devices…

Machine Learning · Computer Science 2025-05-05 Chi-Heng Lin , Shangqian Gao , James Seale Smith , Abhishek Patel , Shikhar Tuli , Yilin Shen , Hongxia Jin , Yen-Chang Hsu

Depth pruning improves the inference efficiency of large language models by removing Transformer blocks. Prior work typically treats layer redundancy as an inherent structural property of pretrained networks, emphasizing importance criteria…

Machine Learning · Computer Science 2026-05-28 Minkyu Kim , Vincent-Daniel Yun , Youngrae Kim , Suin Cho , Woosang Lim , Sunwoo Lee

Deep neural networks have achieved increasingly accurate results on a wide variety of complex tasks. However, much of this improvement is due to the growing use and availability of computational resources (e.g use of GPUs, more layers, more…

Machine Learning · Computer Science 2018-08-03 Ini Oguntola , Subby Olubeko , Christopher Sweeney

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

Computation and Language · Computer Science 2022-01-19 Dongkuan Xu , Ian E. H. Yen , Jinxi Zhao , Zhibin Xiao

Deep neural networks have been the predominant paradigm in machine learning for solving cognitive tasks. Such models, however, are restricted by a high computational overhead, limiting their applicability and hindering advancements in the…

Machine Learning · Computer Science 2024-11-05 Ian Pons , Bruno Yamamoto , Anna H. Reali Costa , Artur Jordao

Channel pruning is one of the major compression approaches for deep neural networks. While previous pruning methods have mostly focused on identifying unimportant channels, channel pruning is considered as a special case of neural…

Computer Vision and Pattern Recognition · Computer Science 2021-09-15 Xiangcheng Liu , Jian Cao , Hongyi Yao , Wenyu Sun , Yuan Zhang

With the successful application of deep learning in communications systems, deep neural networks are becoming the preferred method for signal classification. Although these models yield impressive results, they often come with high…

Machine Learning · Computer Science 2024-06-13 Yao Lu , Yutao Zhu , Yuqi Li , Dongwei Xu , Yun Lin , Qi Xuan , Xiaoniu Yang

Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate…

Computation and Language · Computer Science 2022-07-01 Jingping Liu , Yuqiu Song , Kui Xue , Hongli Sun , Chao Wang , Lihan Chen , Haiyun Jiang , Jiaqing Liang , Tong Ruan

Various applications in the field of autonomous driving are based on convolutional neural networks (CNNs), especially for processing camera data. The optimization of such CNNs is a major challenge in continuous development. Newly learned…

Channel pruning is one of the predominant approaches for deep model compression. Existing pruning methods either train from scratch with sparsity constraints on channels, or minimize the reconstruction error between the pre-trained feature…

Computer Vision and Pattern Recognition · Computer Science 2019-01-15 Zhuangwei Zhuang , Mingkui Tan , Bohan Zhuang , Jing Liu , Yong Guo , Qingyao Wu , Junzhou Huang , Jinhui Zhu

Diffusion Transformers have demonstrated remarkable capabilities in image generation but often come with excessive parameterization, resulting in considerable inference overhead in real-world applications. In this work, we present…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Gongfan Fang , Kunjun Li , Xinyin Ma , Xinchao Wang